Estimating the Real-World Benefits of Lane Departure Warning and Lane Keeping Assist

2022-01-0816

03/29/2022

Features
Event
WCX SAE World Congress Experience
Authors Abstract
Content
Four crash modes are overrepresented in traffic fatalities: run-off-road crashes, non-tracking run-off-road crashes, head-on crashes, and pedestrian crashes. Two advanced driver assist systems developed to help prevent tracking run-off-road crashes and head-on crashes are lane departure warning (LDW) and lane keeping assist (LKA). LDW acts to warn the driver when they are encroaching the lane boundary, whereas LKA performs automatic steering to prevent the vehicle from departing the lane. The objective of this research was to use real-world crash data to estimate current LDW and LKA system effectiveness in reducing run-off-road crashes and cross-centerline head-on crashes.
All passenger vehicles that experienced a lane departure from 2017 to 2019 in the Crash Investigation Sampling System (CISS) were analyzed. The effectivenesses of the LDW and LKA systems were computed using the quasi-induced exposure method, where the exposure group was vehicles that were rear-struck in rear-end crashes.
There were an estimated 470,944 vehicle lane departure crashes. Of the vehicles involved in these events, LDW was available in 33,728 of them and LKA was available in 11,138. Our study estimated that LDW and LKA were effective in reducing the overall number of target population crashes by 3.0% ± 32% and 60% ± 16%, respectively. LKA avoided more crashes than LDW because LKA begins evasive action earlier than the driver. Future work should compare lane centering systems to general lane keeping systems, as lane centering may be even more effective in preventing lane departure crashes.
Meta TagsDetails
DOI
https://doi.org/10.4271/2022-01-0816
Pages
5
Citation
Dean, M., and Riexinger, L., "Estimating the Real-World Benefits of Lane Departure Warning and Lane Keeping Assist," SAE Technical Paper 2022-01-0816, 2022, https://doi.org/10.4271/2022-01-0816.
Additional Details
Publisher
Published
Mar 29, 2022
Product Code
2022-01-0816
Content Type
Technical Paper
Language
English